Knowledge editing methods for large language models are commonly evaluated using predefined benchmarks that assess edited facts together with a limited set of related or neighboring knowledge. While effective, such evaluations remain confined to finite, dataset-bounded samples, leaving the broader impact of editing on the model's knowledge system insufficiently understood. To address this gap, we introduce Embedding-Virtualized Knowledge (EVK) that characterizes model knowledge through controlled perturbations in embedding space, enabling the exploration of a substantially broader and virtualized knowledge region beyond explicit data annotations. Based on EVK, we construct an embedding-level evaluation benchmark EVK-Bench that quantifies potential knowledge drift induced by editing, revealing effects that are not captured by conventional sample-based metrics. Furthermore, we propose a plug-and-play EVK-Align module that constrains embedding-level knowledge drift during editing and can be seamlessly integrated into existing editing methods. Experiments demonstrate that our approach enables more comprehensive evaluation while significantly improving knowledge preservation without sacrificing editing accuracy.

翻译：大型语言模型的知识编辑方法通常通过预定义基准进行评估，这些基准在评估已编辑事实的同时，仅涉及有限的相关或邻近知识集。虽然这类评估方法有效，但其仍局限于有限的、数据集约束的样本，导致编辑对模型知识体系的广泛影响未能得到充分理解。为弥补这一不足，我们提出了嵌入虚拟化知识方法，该方法通过在嵌入空间实施受控扰动来表征模型知识，从而能够探索远超显式数据标注范围的、更广泛且虚拟化的知识区域。基于EVK，我们构建了嵌入层面的评估基准EVK-Bench，用以量化编辑可能引发的知识漂移，揭示传统基于样本的度量方法无法捕捉的潜在影响。此外，我们提出了一种即插即用的EVK-Align模块，该模块能在编辑过程中约束嵌入层面的知识漂移，并可无缝集成到现有编辑方法中。实验表明，我们的方法在实现更全面评估的同时，能够在不牺牲编辑准确性的前提下显著提升知识保存效果。